access icon free Feature selection-based approach for urban short-term travel speed prediction

© The Institution of Engineering and Technology
Received 25/02/2017, Accepted 28/01/2018, Revised 23/12/2017, Published 31/01/2018

This study proposes a feature selection-based approach to identify reasonable spatial–temporal traffic patterns related to the target link, in order to improve the online-prediction performance. The prediction task is composed of two steps: one hybrid intelligent algorithm-based feature selector (FS) is proposed to optimise original state vectors, which are designed empirically during the offline process and optimised state vectors are employed to carry out the online prediction. Numerical experiments by three non-parametric algorithms are conducted with taxis’ global positioning system data in an urban road network of Changsha, China. It is concluded that: (i) under optimised state vectors, the prediction accuracies improve or almost maintain the same; (ii) K-nearest neighbour (KNN) with the simplest state vectors obtains the greatest improvement of prediction performance; (iii) although the performance improvement of ɛ-support vector regression is limited with optimised state vectors, it always outperforms backward-propagation neural network and KNN; and (iv) three non-parametric approaches with optimised state vectors outperform auto-regressive integrated moving average in relatively longer prediction horizons. In conclusion, such FS-based approach is able to improve or guarantee the prediction performance under the remarkably reduced model complexity, and is a promising methodology for short-term traffic prediction.

Inspec keywords: feature selection; road traffic

Other keywords: FS; KNN; spatial temporal traffic patterns; urban road network; online prediction performance; K-nearest neighbour; Changsha China; hybrid intelligent algorithm; feature selection; urban short-term travel speed prediction; target link; global positioning system data

Subjects: Systems theory applications in transportation

References

    1. 1)
      • 1. Vlahogianni, E.I., Karlaftis, M.G., Golias, J.C.: ‘Short-term traffic forecasting: where we are and where we're going’, Transp. Res. C, Emerg. Technol., 2014, 43, pp. 3–19.
    2. 2)
      • 9. Kamarianakis, Y., Gao, H., Prastacos, P.: ‘Characterizing regimes in daily cycles of urban traffic using smooth-transition regressions’, Transp. Res. C, Emerg. Technol., 2010, 18, (5), pp. 821–840.
    3. 3)
      • 2. Chen, C., Wang, Y., Li, L., et al: ‘The retrieval of intra-day trend and its influence on traffic prediction’, Transp. Res. C, Emerg. Technol., 2012, 22, pp. 103–118.
    4. 4)
      • 3. Haworth, J., Cheng, T.: ‘Non-parametric regression for space–time forecasting under missing data’, Comput. Environ. Urban Syst., 2012, 36, (6), pp. 538–550.
    5. 5)
      • 50. Yao, B., Chen, C., Cao, Q., et al: ‘Short-term traffic speed prediction for an urban corridor’, Comput.-Aided Civ. Infrastruct. Eng., 2017, 32, (2), pp. 154–169.
    6. 6)
      • 39. Hosseini, S.H., Moshiri, B., Rahimi-Kian, A., et al: ‘Traffic speed prediction using mutual information’. Proc. Canadian Conf. Electrical and Computer Engineering, Montreal, 2012, pp. 1–4.
    7. 7)
      • 4. Kamarianakis, Y., Shen, W., Wynter, L.: ‘Real-time road traffic forecasting using regime-switching space–time models and adaptive LASSO’, Appl. Stoch. Models Bus. Ind., 2012, 28, (4), pp. 297–315.
    8. 8)
      • 21. Griffith, D.A.: ‘Modeling spatio-temporal relationships: retrospect and prospect’, J. Geogr. Syst., 2010, 12, (2), pp. 111–123.
    9. 9)
      • 51. Clark, S.: ‘Traffic prediction using multivariate nonparametric regression’, J. Transp. Eng., 2003, 129, (2), pp. 161–168.
    10. 10)
      • 5. Du, L., Peeta, S., Kim, Y.H.: ‘An adaptive information fusion model to predict the short-term link travel time distribution in dynamic traffic networks’, Transp. Res. B, Methodol., 2012, 46, (1), pp. 235–252.
    11. 11)
      • 33. Li, W.T.: ‘Mutual information functions versus correlation functions’, J. Stat. Phys., 1990, 60, pp. 823–837.
    12. 12)
      • 23. Mai, T., Ghosh, B., Wilson, S.: ‘Short-term traffic-flow forecasting with auto-regressive moving average models’. Proc. the Inst. Civil Eng. Transp., 2015, 167, (4), pp. 232–239.
    13. 13)
      • 20. Fusco, G., Colombaroni, C., Isaenko, N.: ‘Comparative analysis of implicit models for real-time short-term traffic predictions’, IET Intell. Transp. Syst., 2016, 10, (4), pp. 270–278.
    14. 14)
      • 46. Salvo, G., Amato, G., Zito, P.: ‘Bus speed estimation by neural networks to improve the automatic fleet management’, Eur. Transp., 2007, 51, (37), pp. 93–104.
    15. 15)
      • 41. Affonso, C., Sassi, R.J., Ferreira, R.P.: ‘Traffic flow breakdown prediction using feature reduction through rough-neuro fuzzy networks’. Proc. Int. Conf. neural networks, San Jose, CA, USA, 2011, pp. 1943–1947.
    16. 16)
      • 48. Ye, Q., Szeto, W.Y., Wong, S.C.: ‘Short-term traffic speed forecasting based on data recorded at irregular intervals’, IEEE Trans. Intell. Transp. Syst., 2012, 13, (4), pp. 1727–1737.
    17. 17)
      • 31. Pawlak, Z.: ‘Rough sets: theoretical aspects of reasoning about data’ (Kluwer Academic Publishing, Dordrecht, 1991).
    18. 18)
      • 34. Battiti, R.: ‘Using mutual information for selecting features in supervised neural net learning’, IEEE Trans. Neural Netw., 1994, 5, (4), pp. 537–550.
    19. 19)
      • 27. Jolliffe, T.: ‘Principal component analysis’. ACM Computing Surveys, 1986, pp. 1–47.
    20. 20)
      • 19. Fusco, G., Colombaroni, C., Isaenko, N.: ‘Short-term speed predictions exploiting big data on large urban road networks’, Transp. Res. C, Emerg. Technol., 2016, 73, pp. 183–201.
    21. 21)
      • 37. Sun, Z., Wang, Y., Pan, J.: ‘Short-term traffic flow forecasting based on clustering and feature selection’. Proc. Int. Conf. Neural Networks, Hong Kong, 2008, pp. 577–583.
    22. 22)
      • 18. Lv, Y., Duan, Y., Kang, W., et al: ‘Traffic flow prediction with big data: a deep learning approach’, IEEE Trans. Intell. Transp. Syst., 2015, 16, pp. 865–873.
    23. 23)
      • 30. Rasyidi, M.A., Ryu, K.R.: ‘Short-term speed prediction on urban highways by ensemble learning with feature subset selection’. Proc. Int. Conf. Data Systems for Advanced Applications, 2014, PP. pp. 46–60.
    24. 24)
      • 40. Yang, S.: ‘On feature selection for traffic congestion prediction’, Transp. Res. C, Emerg. Technol., 2013, 26, pp. 160–169.
    25. 25)
      • 53. Yun, S., Namkoong, S., Rho, J., et al: ‘A performance evaluation of neural network models in traffic volume forecasting’, Math. Comput. Model., 1998, 27, (2), pp. 293–310.
    26. 26)
      • 29. Uguz, H.: ‘A two-stage feature selection method for text categorization by using information gain, principal component analysis and genetic algorithm’, Knowl.-Based Syst., 2011, 24, pp. 1024–1032.
    27. 27)
      • 54. Vapnik, V., Lerner, A.: ‘Pattern recognition using generalized portrait method’, Autom. Remote Control, 1963, 24, pp. 774–780.
    28. 28)
      • 42. Vlahogianni, E.I., Karlaftis, M.G.: ‘Fuzzy-entropy neural network freeway incident duration modeling with single and competing uncertainties’, Comput.-Aided Civ. Infrastruct. Eng., 2013, 28, pp. 420–433.
    29. 29)
      • 7. Yildirim, U., Çataltepe, Z.: ‘Short time traffic speed prediction using data from a number of different sensor locations’.  23rd Int. Symp. Computer and Information Sciences ISCIS'08, 2008, pp. 1–6.
    30. 30)
      • 47. Poomrittigul, S., Pan-ngum, S., Phiu-Nual, K., et al: ‘Mean travel speed estimation using GPS data without ID number on inner city road’. Proc. Int. Conf. ITS Telecommunications, 2008, pp. 56–61.
    31. 31)
      • 17. Li, L., Su, X., Wang, Y., et al: ‘Robust causal dependence mining in big data network and its application to traffic flow predictions’, Transp. Res. C, Emerg. Technol., 2015, 58, pp. 292–307.
    32. 32)
      • 36. Cheng, T., Haworth, J., Wang, J.: ‘Spatio-temporal autocorrelation of road network data’, J. Geogr. Syst., 2012, 14, (4), pp. 389–413.
    33. 33)
      • 25. Kohavi, R, John, G.H.: ‘Wrappers for feature subset selection’, Artif. Intell., 1997, 97, pp. 273–324.
    34. 34)
      • 6. Sun, S., Huang, R., Gao, Y.: ‘Network-scale traffic modeling and forecasting with graphical lasso and neural networks’, J. Transp. Eng., 2012, 138, (11), pp. 1358–1367.
    35. 35)
      • 15. Oh, C., Park, S.: ‘Investigating the effects of daily travel time patterns on short-term prediction’, Korean Soc. Civ. Eng. J. Civ. Eng., 2011, 15, (7), pp. 1263–1272.
    36. 36)
      • 13. Zou, N., Wang, J., Chang, G.L., et al: ‘Field test of a travel-time prediction system with widely spaced detectors transportation research record’, J. Transp. Res. Rec. Board, 2009, 2129, (1), pp. 62–72.
    37. 37)
      • 16. Cai, P., Wang, Y., Lu, G., et al: ‘A spatiotemporal correlative k-nearest neighbor model for short-term traffic multistep forecasting’, Transp. Res. C, Emerg. Technol., 2016, 62, pp. 21–34.
    38. 38)
      • 24. Zou, Y., Zhu, X., Zhang, Y., et al: ‘A space–time diurnal method for short-term freeway travel time prediction’, Transp. Res. C, Emerg. Technol., 2014, 43, pp. 33–49.
    39. 39)
      • 35. Chow, T., Huang, D.: ‘Estimating optimal feature subsets using efficient estimation of high-dimensional mutual information’, IEEE Trans. Neural Netw., 2005, 6, (1), pp. 213–224.
    40. 40)
      • 43. Dong, N., Huang, H., Zheng, L.: ‘Support vector machine in crash prediction at the level of traffic analysis zones: assessing the spatial proximity effects’, Accid. Anal. Prev., 2014, 82, pp. 192–198.
    41. 41)
      • 38. Hosseini, S.H., Moshiri, B., Rahimi-Kian, A., et al: ‘Short-term traffic flow forecasting by mutual information and artificial neural networks’. Proc. Int. Conf. Industrial Technology, Athens, 2012, pp. 1136–1141.
    42. 42)
      • 8. Chandra, S.R., Al-Deek, H.: ‘Predictions of freeway traffic speeds and volumes using vector autoregressive models’, J. Intell. Transp. Syst., 2009, 13, (2), pp. 53–72.
    43. 43)
      • 44. Shiau, Y., Tsai, C., Hung, Y., et al: ‘The application of data mining technology to build a forecasting model for classification of road traffic accidents’, Math. Probl. Eng., 2015, 170635, pp. 1–8.
    44. 44)
      • 52. Richards, P.I.: ‘Shock waves on the highway’, Oper. Res., 1956, 4, (1), pp. 42–51.
    45. 45)
      • 49. Julio, N., Giesen, R., Lizana, P.: ‘Real-time prediction of bus travel speeds using traffic shockwaves and machine learning algorithms’, Res. Transp. Econ., 2016, 59, pp. 250–257.
    46. 46)
      • 32. Shannon, C.E.: ‘A mathematical theory of communication’, Bell Lab. Tech. J., 1948, 27, (4), pp. 623–656.
    47. 47)
      • 22. Kamarianakis, Y., Prastacos, P.: ‘Space–time modeling of traffic flow’, Comput. Geosci., 2005, 31, (2), pp. 119–133.
    48. 48)
      • 14. Wang, J., Shang, P., Zhao, X.: ‘A new traffic speed forecasting method based on bi-pattern recognition’, Fluct. Noise Lett., 2011, 10, (1), pp. 59–75.
    49. 49)
      • 26. Hall, M.A., Smith, L.A.: ‘Feature subset selection: a correlation based filter approach’. Proc. Int. Conf. Neural Information Processing and Intelligent Information Systems, 1997, pp. 855–888.
    50. 50)
      • 11. Stathopoulos, A., Karlaftis, M.G.: ‘A multivariate state-space approach for urban traffic flow modeling and prediction’, Transp. Res. C, Emerg. Technol., 2003, 11, (2), pp. 121–135.
    51. 51)
      • 12. Turochy, R.: ‘Enhancing short-term traffic forecasting with traffic condition information’, J. Transp. Eng., 2006, 132, (6), pp. 469–474.
    52. 52)
      • 10. Wu, S., Yang, Z., Zhu, X., et al: ‘Improved k-NN for short-term traffic forecasting using temporal and spatial information’, J. Transp. Eng., 2014, 140, (7), pp. 46–60.
    53. 53)
      • 45. Chen, X., Wei, Z., Liu, X., et al: ‘Spatiotemporal variable and parameter selection using sparse hybrid genetic algorithm for traffic flow forecasting’, Int. J. Distrib. Sens. Netw., 2017, 13, (6), p. 1550147717713376.
    54. 54)
      • 28. Calvo, B., Larrañaga, P., Lozano, J.A.: ‘Feature subset selection from positive and unlabelled examples’, Pattern Recognit. Lett., 2009, 30, pp. 1027–1036.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-its.2017.0059
Loading

Related content

content/journals/10.1049/iet-its.2017.0059
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading